© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5592
    Prev
    Next
    INDEX
    Explanations

    the term 'closely' in various contexts of collaboration or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Read
    -0.66
    tude
    -0.58
    de
    -0.56
    id
    -0.56
     effect
    -0.55
    o
    -0.55
    ondissement
    -0.55
     Ok
    -0.54
    ↵
    -0.54
     H
    -0.52
    POSITIVE LOGITS
    AndEndTag
    1.00
     HasFactory
    0.97
     كومونز
    0.97
     greateſt
    0.94
    ReusableCell
    0.93
     vectorstock
    0.92
     closely
    0.91
     OBITUARY
    0.89
     Efq
    0.88
     Theſe
    0.88
    Activations Density 0.055%

    No Known Activations